bioRxiv2018
Allosteric regulation is a well-established phenomenon classically defined as conformational or dynamical change of a small number of allosteric residues of the protein upon allosteric effector binding at a distance. Here, we developed a novel approach to delineate allosteric effects in proteins. In this approach, we applied robust machine learning methods, including Deep Neural Network and Random Forest, on extensive molecular dynamics (MD) simulations to distinguish otherwise similar allosteric states of proteins. Using PDZ3 domain of PDS-95 as a model protein, we demonstrated that the allosteric effects could be represented as residue-specific properties through two-dimensional property-residue maps, which we refer as \"residue perturbation maps\". These maps were constructed through two machine learning methods and could accurately describe how different properties of various residues are affected upon allosteric perturbation on protein. Based on the \"residue perturbation maps\", we propose allostery as a residue-specific concept, suggesting all residues could be considered as allosteric residues because each residue \"senses\" the allosteric events through perturbation of its one or multiple attributes in a quantitatively unique way. The \"residue perturbation maps\" could be used to fingerprint a protein based on the unique patterns of residue perturbations upon binding events, providing a novel way to systematically describe the protein allosteric effects of each residue upon perturbation.\n\nAuthor SummaryAllostery is protein regulation at distance. A perturbation at one site of the protein could distantly affect another site. The residues involved in these sites are considered as allosteric residues. The allostery concept has been widely used to understand protein mechanisms and to design allosteric drugs. It is long believed only a small number of residues are allosteric residues. Here, we argue that all residues in a protein are allosteric residues. Upon the perturbation of the allosteric events, the different properties of each residue are affected at the distinct extend. We used hybrid models including molecular dynamics simulations and machine learning components to reveal that not only many properties of residues are affected upon ligand binding, but also each residue is affected through perturbation of its various properties, which makes the residue distinguishable from other residues. According to our findings in a model protein, we defined a \"residue perturbation map\" as a two-dimensional map that fingerprint a protein based on the extent of perturbation in different properties of all its residues in a quantitative fashion. This \"residue perturbation map\" provides a novel way to systematically describe the protein allosteric effects of each residue upon perturbation.